A GIS device monitoring method and system based on image recognition

Abstract

The application is suitable for the technical field of power equipment monitoring, and provides a GIS equipment monitoring method and system based on image recognition, which is suitable for GIS equipment, the GIS equipment comprising a shell, a sealing flange being installed at a connecting position of the shell, and sulfur hexafluoride gas being filled in the shell, the method comprising: acquiring a to-be-detected grayscale image of the GIS equipment; determining a first target region in the to-be-detected grayscale image according to first grayscale value information of each pixel point in the to-be-detected grayscale image; determining first position information corresponding to the first target region and second position information corresponding to a second target region in the to-be-detected grayscale image based on the to-be-detected grayscale image and a preset target detection algorithm; and determining prediction position information according to the first position information and the second position information. The application can help operation and maintenance personnel to effectively determine the position of a gas leakage point, greatly improve the maintenance efficiency, and shorten the maintenance time.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power equipment monitoring, in particular to a GIS device monitoring method and system based on image recognition. BACKGROUND

[0002] Gas Insulated Switchgear (GIS) device is one of important switch type power equipment; GIS device effectively protects busbars, transformers, arresters, circuit breakers and disconnectors and other power devices through a closed grounding metal shell, which is usually combined by a sealing flange and a plurality of relatively smaller shells; in order to reduce the situation that the power devices are broken down by high-voltage arc, sulfur hexafluoride gas is usually filled in the GIS device.

[0003] At present, since the sealing ring in the sealing flange is aging, sulfur hexafluoride gas leakage usually occurs at the position of the sealing flange; the operator usually uses a thermal imager to determine the gas leakage point on the sealing flange, but when at least two gas leakage points are close to each other, the operator can only determine a rough gas leakage range, which is not conducive to effectively determining the position of the gas leakage point, and needs to be further improved. SUMMARY

[0004] Therefore, the embodiments of the present application provide a GIS device monitoring method and system based on image recognition to solve the problem that the position of the gas leakage point cannot be effectively determined in the prior art.

[0005] In a first aspect, the embodiments of the present application provide a GIS device monitoring method based on image recognition, which is suitable for a GIS device, the GIS device includes a shell, a sealing flange is installed at the connection of the shell, and sulfur hexafluoride gas is filled in the shell, and the method includes:

[0006] obtaining a to-be-detected gray image of the GIS device;

[0007] determining a first target region in the to-be-detected gray image according to first gray value information of each pixel point in the to-be-detected gray image, wherein second gray value information of the first target region is smaller than third gray value information of a neighboring region, and the neighboring region is used to describe a region adjacent to the first target region;

[0008] determining first position information corresponding to the first target region and second position information corresponding to a second target region in the to-be-detected gray image based on the to-be-detected gray image and a preset target detection algorithm, wherein the second target region is used to describe a region corresponding to the sealing flange in the to-be-detected gray image;

[0009] According to the first position information and the second position information, predicted position information is determined, wherein the predicted position information is used to describe a predicted position corresponding to the gas leakage point in the GIS device.

[0010] Compared with the prior art, the GIS device monitoring method based on image recognition provided in the embodiments of the present application has the beneficial effects that: the terminal device can first acquire a to-be-detected gray image of the GIS device, then determine a first target region according to first gray value information of each pixel point in the to-be-detected gray image, and then determine first position information corresponding to the first target region and second position information corresponding to a second target region based on the to-be-detected gray image and a preset target detection algorithm, and then determine predicted position information according to the first position information and the second position information, so that even if at least two gas leakage points are relatively close, the predicted position information can provide a predicted position of a gas leakage point for an operation and maintenance personnel, which is conducive to the operation and maintenance personnel to effectively determine the position of the gas leakage point, effectively reduce the troubleshooting range of the operation and maintenance personnel, greatly improve the maintenance efficiency, and to a certain extent, solve the problem that it is not conducive to effectively determining the position of the gas leakage point.

[0011] In a second aspect, the embodiments of the present application provide a GIS device monitoring system based on image recognition, which is suitable for a GIS device, the GIS device comprising a shell, a sealing flange being installed at a connection of the shell, and sulfur hexafluoride gas being filled in the shell, and the system comprising:

[0012] a to-be-detected gray image acquisition module configured to acquire a to-be-detected gray image of the GIS device;

[0013] a first target region determination module configured to determine a first target region in the to-be-detected gray image according to first gray value information of each pixel point in the to-be-detected gray image, wherein second gray value information of the first target region is smaller than third gray value information of a neighboring region adjacent to the first target region;

[0014] a position information determination module configured to determine first position information corresponding to the first target region and second position information corresponding to a second target region in the to-be-detected gray image based on the to-be-detected gray image and a preset target detection algorithm, wherein the second target region is used to describe a region corresponding to the sealing flange in the to-be-detected gray image;

[0015] a predicted position information determination module configured to determine predicted position information according to the first position information and the second position information, wherein the predicted position information is used to describe a predicted position corresponding to the gas leakage point in the GIS device.

[0016] In a third aspect, an embodiment of the present application provides a terminal device, comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, and the processor implements the steps of the method of the first aspect when executing the computer program.

[0017] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the steps of the method of the first aspect.

[0018] It can be understood that the beneficial effects of the second aspect to the fourth aspect can be referred to the related description in the first aspect, which will not be repeated here. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiments or prior art description will be briefly introduced as follows.

[0020] Figure 1 is a flowchart of a GIS device monitoring method provided by an embodiment of the present application;

[0021] Figure 2 is a schematic diagram of a GIS device provided by an embodiment of the present application;

[0022] Figure 3 is a flowchart of step S200 in the GIS device monitoring method provided by an embodiment of the present application;

[0023] Figure 4 is a first schematic diagram of a pixel point provided by an embodiment of the present application;

[0024] Figure 5 is a second schematic diagram of a pixel point provided by an embodiment of the present application;

[0025] Figure 6 is a flowchart of the GIS device monitoring method provided by an embodiment of the present application before step S210;

[0026] Figure 7 is a third schematic diagram of a pixel point provided by an embodiment of the present application;

[0027] Figure 8 is a fourth schematic diagram of a pixel point provided by an embodiment of the present application;

[0028] Figure 9 is a flowchart of step S400 in the GIS device monitoring method provided by an embodiment of the present application;

[0029] Figure 10is a module block diagram of a GIS device monitoring system provided by an embodiment of the present application.

[0030] Figure 11 is a schematic diagram of a terminal device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0031] In the following description, for the purpose of explanation and not limitation, specific details are set forth, such as particular system configurations, techniques, etc., in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application can be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

[0032] In the description of the present application and the appended claims, the terms "first", "second", "third", etc. are used only to distinguish descriptions, and cannot be understood as indicating or implying relative importance.

[0033] In the present application, the reference "one embodiment" or "some embodiments" means that the specific features, structures or characteristics described in connection with the embodiment are included in one or more embodiments of the present application. Therefore, the statements "in one embodiment", "in some embodiments", "in other some embodiments", "in other some embodiments" and the like appearing in different places in the specification are not necessarily all referring to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized. The terms "include", "contain", "have" and their variants mean "include but not limited to", unless otherwise specifically emphasized.

[0034] In order to illustrate the technical solutions described in the present application, the following will be described by specific embodiments.

[0035] Please refer to Figure 1 , Figure 1 is a flowchart of a GIS device monitoring method based on image recognition provided by an embodiment of the present application. In the present embodiment, the execution subject of the GIS device monitoring method is a terminal device. It can be understood that the types of the terminal device include but are not limited to mobile phones, tablet computers, notebook computers, ultra-mobile personal computers (UMPC), netbooks, personal digital assistants (PDA) and the like, and the specific type of the terminal device is not limited by the present embodiment.

[0036] Please refer to Figure 1The GIS device monitoring method provided by the embodiments of the present application includes but is not limited to the following steps:

[0037] In S100, a to-be-detected gray image of the GIS device is acquired.

[0038] Without loss of generality, please refer to Figure 2 The GIS device monitoring method can be applied to a gas insulated switchgear (GIS) device, which includes a shell, a sealing flange installed at a connection of the shell, and sulfur hexafluoride gas filled in the shell.

[0039] Specifically, the to-be-detected gray image is used to describe a gray image of the object being the GIS device; and the terminal device can first acquire the to-be-detected gray image of the GIS device.

[0040] In some possible implementation manners, in order to improve the effectiveness of the to-be-detected gray image, before S100, the method further includes but is not limited to the following steps:

[0041] In S101, a to-be-detected infrared image of the GIS device is acquired based on a preset infrared thermal imager.

[0042] Without loss of generality, since the sulfur hexafluoride gas in the GIS device can leak to the outside of the GIS device from a leakage point on the sealing flange, and the sulfur hexafluoride gas can absorb infrared rays to generate a specific infrared absorption spectrum line, the operation and maintenance personnel can preinstall a plurality of infrared thermal imagers in the peripheral area of the GIS device, and the lenses of the plurality of infrared thermal imagers are respectively directed toward the sealing flanges on the GIS device, and each sealing flange is observed by at least one infrared thermal imager.

[0043] Specifically, the to-be-detected infrared image is used to describe an infrared image of the shooting object being the sealing flange; and the terminal device can acquire the to-be-detected infrared image of the GIS device based on the preset infrared thermal imager.

[0044] Correspondingly, S100 includes but is not limited to the following steps:

[0045] In S110, the to-be-detected infrared image is subjected to gray processing to generate the to-be-detected gray image of the GIS device.

[0046] Specifically, the to-be-detected gray image is used to describe the to-be-detected infrared image after the gray processing; since the average method, which is one of common gray processing methods of images, can obtain a gray image in which a dark place is darker than other colors, after the terminal device acquires the to-be-detected infrared image, the terminal device can perform the gray processing on the to-be-detected infrared image based on the average method to generate the to-be-detected gray image of the GIS device.

[0047] In S200, according to the first gray value information of each pixel point in the to-be-detected gray image, a first target region in the to-be-detected gray image is determined.

[0048] Without loss of generality, the first gray value information is used to describe the gray value corresponding to the pixel point in the to-be-detected gray image, the value range of the gray value is 0 to 255, the gray value of 0 represents black, and the gray value of 255 represents white; the first target region can be one pixel point, and the first target region can also be composed of multiple pixel points; the second gray value information is used to describe the gray value corresponding to the first target region, when the first target region is one pixel point, the second gray value information can be the first gray value information corresponding to the pixel point, when the first target region is composed of multiple pixel points, the second gray value information can be the average value of the sum of the first gray value information corresponding to the pixel points; the third gray value information is used to describe the gray value corresponding to the adjacent region, the adjacent region is used to describe the region adjacent to the first target region, and the second gray value information of the first target region is smaller than the third gray value information of the adjacent region;

[0049] Specifically, the terminal device can determine the first target region in the to-be-detected gray image according to the first gray value information of each pixel point in the to-be-detected gray image.

[0050] In some possible implementation manners, in order to facilitate accurate determination of the first target region, referring to Figure 3 , step S200 includes but is not limited to the following steps:

[0051] In S210, the first gray value information corresponding to each pixel point in the to-be-detected gray image is obtained.

[0052] Specifically, the terminal device first obtains the first gray value information corresponding to each pixel point in the to-be-detected gray image.

[0053] In S220, the first gray value information corresponding to each pixel point is compared with a preset first gray threshold value respectively, and a target pixel point is determined.

[0054] Specifically, the fourth gray value information is used to describe the gray value of the target pixel point, the fourth gray value information of the target pixel point is less than or equal to the first gray threshold value, and the first gray threshold value can be any integer between 0 and 30, such as 0, 8, or 30.

[0055] Exemplarily, referring to Figure 4 , Figure 4The 20 rectangles marked with numbers in the middle each represent a pixel point, and the number in the rectangle represents the first gray value information corresponding to the pixel point; the first gray threshold can be preset as 30, and the terminal device can compare the first gray value information corresponding to each pixel point with the preset first gray threshold to determine the target pixel point, Figure 4 The four rectangles marked with hatch lines in the middle (i.e., the rectangle marked with the number 2, the rectangle marked with the number 9, the rectangle marked with the number 15, and the rectangle marked with the number 29) each represent a target pixel point.

[0056] In S230, for each target pixel point: obtain the fifth gray value information of the adjacent pixel point.

[0057] Specifically, referring to Figure 4 , the adjacent pixel points can be the rectangle marked with the number 153, the rectangle marked with the number 44, the rectangle marked with the number 65, the rectangle marked with the number 82, the rectangle marked with the number 179, the rectangle marked with the number 53, the rectangle marked with the number 131, and the rectangle marked with the number 176; the terminal device can process each target pixel point as follows: obtain the fifth gray value information of the adjacent pixel point.

[0058] In S240, generate the gray difference value information according to the fifth gray value information and the fourth gray value information.

[0059] Specifically, the gray difference value information is used to describe the difference between the fifth gray value information and the fourth gray value information; after the terminal device obtains the fifth gray value information, the terminal device can generate the gray difference value information according to the fifth gray value information and the fourth gray value information.

[0060] In S250, compare the gray difference value information with the preset second gray threshold.

[0061] Specifically, after the terminal device generates the gray difference value information, the terminal device can compare the gray difference value information with the preset second gray threshold, and the second gray threshold can be 30.

[0062] In S260, if the gray difference value information is less than or equal to the second gray threshold, merge the adjacent pixel point and the target pixel point to generate the first target region.

[0063] Exemplarily, referring to Figure 4 and Figure 5 , in Figure 4For example, when the second gray threshold is set as 30, the gray difference information between the target pixel point corresponding to the rectangle marked with the number 29 and the adjacent pixel point corresponding to the rectangle marked with the number 53 is 24, the gray difference information between the target pixel point corresponding to the rectangle marked with the number 15 and the adjacent pixel point corresponding to the rectangle marked with the number 44 is 29, and the terminal device can combine the adjacent pixel point corresponding to the rectangle marked with the number 53, the adjacent pixel point corresponding to the rectangle marked with the number 44 and the target pixel point to generate a first target region, i.e. Figure 5 For example, the rectangle with four thick edges.

[0064] In some possible implementation manners, in order to more accurately determine the first target region, please refer to Figure 6 Before step S210, the method further includes but is not limited to the following steps:

[0065] In S201, for each pixel point: compare the first gray value information with a preset third gray threshold.

[0066] Specifically, the terminal device can perform the following processing on each pixel point: the terminal device can compare the first gray value information with a preset third gray threshold, and the third gray threshold can be set as 50.

[0067] In S202, if the first gray value information is less than or equal to the third gray threshold, calculate the difference between the first gray value information and a preset gray correction value to generate first optimized gray value information corresponding to the pixel point.

[0068] Specifically, the gray correction value can be 10; if the first gray value information is less than or equal to the third gray threshold, the terminal device can calculate the difference between the first gray value information and a preset gray correction value to generate first optimized gray value information corresponding to the pixel point, so as to realize screening of the pixel point with the first gray value information less than or equal to the third gray threshold and optimization of the gray value of the pixel point.

[0069] For example, taking the gray correction value 10 as an example, please refer to Figure 7 , Figure 7 The numbers "0", "5", "19" and "34" marked in the figure represent the first optimized gray value information, Figure 7 The numbers in the brackets represent the original first gray value information.

[0070] In S203, if the first gray value information is greater than the third gray threshold, calculate the sum of the first gray value information and a preset gray correction value to generate second optimized gray value information corresponding to the pixel point.

[0071] Specifically, if the first gray value information is greater than the third gray threshold, the terminal device can calculate the sum of the first gray value information and a preset gray correction value, and generate second optimized gray value information corresponding to the pixel point.

[0072] For example, taking the gray correction value 10 as an example, please refer to Figure 8 , Figure 8 The numbers "255", "186", "141", "145", "250", "163", "63", "224", "108", "189", "184", "68", "75", and "92" in the above table represent the second optimized gray value information.

[0073] Correspondingly, step S220 includes but is not limited to the following steps:

[0074] In S221, for each pixel point: compare the first optimized gray value information corresponding to the pixel point with the preset first gray threshold to determine the target pixel point.

[0075] Specifically, the terminal device can process each pixel point as follows: compare the first optimized gray value information corresponding to the pixel point with the preset first gray threshold to determine the target pixel point. The specific processing process is similar to the corresponding content in step S220 described above, and thus is not described in detail.

[0076] Or

[0077] In S222, compare the second optimized gray value information corresponding to the pixel point with the preset first gray threshold to determine the target pixel point.

[0078] Specifically, the terminal device can process each pixel point as follows: compare the second optimized gray value information corresponding to the pixel point with the preset first gray threshold to determine the target pixel point. The specific processing process is similar to the corresponding content in step S220 described above, and thus is not described in detail.

[0079] In S300, based on the to-be-detected gray image and a preset target detection algorithm, determine first position information corresponding to a first target region in the to-be-detected gray image and second position information corresponding to a second target region.

[0080] Without loss of generality, the first position information is used to describe the position of the first target region in the to-be-detected gray image, the second target region is used to describe the region corresponding to the sealing flange in the to-be-detected gray image, the second position information is used to describe the position of the second target region in the to-be-detected gray image, and the target detection algorithm can be a Faster Region-based Convolutional Neural Network (Faster R-CNN) algorithm.

[0081] Specifically, the terminal device can determine first position information corresponding to the first target region in the to-be-detected gray image and second position information corresponding to the second target region in the to-be-detected gray image based on the to-be-detected gray image and the preset target detection algorithm.

[0082] In S400, the predicted position information is determined according to the first position information and the second position information.

[0083] Specifically, the predicted position information is used to describe a predicted position corresponding to the gas leakage point in the GIS device; after the terminal device determines the first position information and the second position information, the terminal device can determine the predicted position information according to the first position information and the second position information.

[0084] In some possible implementation manners, in order to improve the pertinence of the predicted position information, refer to Figure 9 , step S400 includes but is not limited to the following steps:

[0085] In S410, the first overlap region is determined according to the first position information and the second position information.

[0086] Specifically, the first overlap region is used to describe a region in which the first position information and the second position information overlap; the terminal device can determine the first overlap region according to the first position information and the second position information.

[0087] Exemplarily, in order to cope with the case that the first position information and the second position information partially overlap, the terminal device can construct a plane coordinate system of the to-be-detected gray image, then determine first coordinates of each pixel point in the first target region according to the first position information, determine second coordinates of each pixel point in the second target region according to the second position information, then compare the first coordinates and the second coordinates in sequence, if the first coordinates are equal to the second coordinates, it is determined that the pixel point belongs to a component of the first overlap region, and all the pixel points whose first coordinates are equal to the second coordinates are determined, and then the region occupied by the pixel points is determined as the first overlap region.

[0088] In S420, third position information of the first overlap region is acquired, and the third position information is determined as the predicted position information.

[0089] Specifically, after the terminal device determines the first overlap region, the terminal device can acquire third position information of the first overlap region, and determine the third position information as the predicted position information. When at least two gas leakage points are relatively close, the predicted position information provides a reliable reference value for the operation and maintenance personnel, thereby facilitating the operation and maintenance personnel to effectively determine the position of the gas leakage point, improving the maintenance efficiency, and shortening the maintenance time.

[0090] In some possible implementation manners, to further facilitate effective determination of the location of the gas leakage point, before step S410, the method further includes but is not limited to the following steps:

[0091] In S401, historical gas leakage location information of the sealing flange is acquired.

[0092] Specifically, the historical gas leakage location information is used to describe the location corresponding to the gas leakage point in the history of the sealing flange, and the historical gas leakage location information can be stored in a preset historical database; the terminal device can acquire the historical gas leakage location information of the sealing flange based on the preset historical database.

[0093] Correspondingly, step S410 includes but is not limited to the following steps:

[0094] In S411, the second overlapping region is determined according to the first location information, the second location information and the historical gas leakage location information.

[0095] Specifically, the second overlapping region is used to describe a region where the first location information, the second location information and the historical gas leakage location information overlap; after the terminal device acquires the historical gas leakage location information, the terminal device can determine the second overlapping region according to the first location information, the second location information and the historical gas leakage location information, thereby further facilitating effective determination of the location of the gas leakage point by the operation and maintenance personnel.

[0096] The implementation principle of the GIS device monitoring method based on image recognition in the embodiment of the application is as follows: the terminal device can first acquire a to-be-detected infrared image of the GIS device, then perform grayscale processing on the to-be-detected infrared image to generate a to-be-detected grayscale image of the GIS device, then determine a first target region according to first grayscale value information of each pixel point in the to-be-detected grayscale image, then determine first location information corresponding to the first target region and second location information corresponding to a second target region based on the to-be-detected grayscale image and a preset target detection algorithm, and then determine predicted location information according to the first location information and the second location information, so that even if at least two gas leakage points are relatively close, the predicted location information can provide a predicted location of a gas leakage point for the operation and maintenance personnel, which facilitates effective determination of the location of the gas leakage point by the operation and maintenance personnel, improves the maintenance efficiency, and effectively reduces the troubleshooting range of the operation and maintenance personnel.

[0097] It should be noted that the size of the serial number of each step in the above embodiment does not mean the execution sequence, and the execution sequence of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiment of the application.

[0098] The embodiment of the present application also provides a GIS equipment monitoring system based on image recognition, which is applicable to GIS equipment. The GIS equipment includes a housing, a sealing flange is installed at the connection of the housing, and sulfur hexafluoride gas is filled in the housing. For ease of description, only the parts related to the present application are shown, such as Figure 10 As shown, the system 100 includes:

[0099] Grayscale image acquisition module 110 for obtaining a grayscale image for GIS equipment;

[0100] A first target region determining module 120 is configured to determine a first target region in the grayscale image to be detected based on first grayscale value information of each pixel point in the grayscale image to be detected, wherein the second grayscale value information of the first target region is smaller than the third grayscale value information of the adjacent region, and the adjacent region is used to describe a region adjacent to the first target region;

[0101] Position information determination module 130: configured to determine, based on the grayscale image to be detected and a preset target detection algorithm, first position information corresponding to a first target region in the grayscale image to be detected and second position information corresponding to a second target region, wherein the second target region is used to describe a region corresponding to the sealing flange in the grayscale image to be detected;

[0102] The predicted position information determination module 140 is used to determine the predicted position information based on the first position information and the second position information, wherein the predicted position information is used to describe the predicted position corresponding to the gas leakage point in the GIS device.

[0103] Optionally, the first target area determination module 120 includes:

[0104] The first grayscale value information acquisition submodule is used to obtain the first grayscale value information corresponding to each pixel in the grayscale image to be detected;

[0105] Target pixel determination submodule: used to compare the first grayscale value information corresponding to each pixel with the preset first grayscale threshold, and determine the target pixel, wherein the fourth grayscale value information of the target pixel is less than or equal to the first grayscale threshold;

[0106] The fifth grayscale value information acquisition submodule is used to acquire the fifth grayscale value information of adjacent pixels for each target pixel;

[0107] Grayscale difference information generating submodule: used for generating grayscale difference information according to the fifth grayscale value information and the fourth grayscale value information;

[0108] Grayscale difference information comparison submodule: used to compare the grayscale difference information with a preset second grayscale threshold;

[0109] The first target region generation submodule is configured to: if the gray scale difference value information is less than or equal to a second gray scale threshold value, merge the adjacent pixel points and the pixel point to generate a first target region.

[0110] Optionally, the system 100 further includes:

[0111] The first gray scale value information comparison module is configured to: for each pixel point, compare the first gray scale value information with a preset third gray scale threshold value.

[0112] The first optimized gray scale value information generation module is configured to: if the first gray scale value information is less than or equal to the third gray scale threshold value, calculate a difference between the first gray scale value information and a preset gray scale correction value to generate first optimized gray scale value information corresponding to the pixel point.

[0113] The second optimized gray scale value information generation module is configured to: if the first gray scale value information is greater than the third gray scale threshold value, calculate a sum of the first gray scale value information and the preset gray scale correction value to generate second optimized gray scale value information corresponding to the pixel point.

[0114] Correspondingly, the target pixel point determination submodule includes:

[0115] The target pixel point first determination unit is configured to: for each pixel point, compare the first optimized gray scale value information corresponding to the pixel point with a preset first gray scale threshold value to determine a target pixel point.

[0116] Or

[0117] The target pixel point second determination unit is configured to compare the second optimized gray scale value information corresponding to the pixel point with the preset first gray scale threshold value to determine the target pixel point.

[0118] Optionally, the prediction position information determination module 140 includes:

[0119] The first overlap region determination submodule is configured to determine a first overlap region according to the first position information and the second position information, wherein the first overlap region is used to describe a region where the first position information and the second position information overlap.

[0120] The prediction position information determination submodule is configured to obtain third position information of the first overlap region, and determine the third position information as the prediction position information.

[0121] Optionally, the system 100 further includes:

[0122] The historical gas leakage position information acquisition module is configured to acquire historical gas leakage position information of the sealing flange.

[0123] Correspondingly, the first overlap region determination submodule includes:

[0124] The second overlap area determination unit is configured to determine a second overlap area according to the first position information, the second position information and the historical gas leakage position information, wherein the second overlap area is used to describe an area where the first position information, the second position information and the historical gas leakage position information overlap.

[0125] Optionally, the system 100 further comprises:

[0126] The to-be-detected infrared image acquisition module is configured to acquire a to-be-detected infrared image of the GIS device based on a preset infrared thermal imager.

[0127] Correspondingly, the to-be-detected grayscale image acquisition module 110 comprises:

[0128] The to-be-detected grayscale image generation submodule is configured to perform grayscale processing on the to-be-detected infrared image to generate a to-be-detected grayscale image of the GIS device.

[0129] It should be noted that the information interaction and execution process between the above modules are based on the same concept as the method embodiments of the present application, and the specific functions and technical effects brought by them can be referred to the method embodiments part, which will not be repeated here.

[0130] The present application also provides a terminal device, as shown in the Figure 11 The terminal device 110 of this embodiment comprises a processor 111, a memory 112, and a computer program 113 stored in the memory 112 and executable on the processor 111. When the processor 111 executes the computer program 113, it implements the steps in the flow processing method embodiments described above, such as Figure 1 The steps S100 to S400 shown in the figure; or, when the processor 111 executes the computer program 113, it implements the functions of the modules in the above-described apparatus, such as Figure 10 The functions of the modules 110 to 140 shown in the figure.

[0131] The terminal device 110 can be a desktop computer, a notebook computer, a palm computer, and a cloud server, etc. The terminal device 110 includes but is not limited to the processor 111 and the memory 112. Those skilled in the art can understand that Figure 11 The terminal device 110 is only an example and does not constitute a limitation on the terminal device 110, which can include more or fewer components than shown, or combine certain components, or different components, for example, the terminal device 110 can also include input / output devices, network access devices, buses, etc.

[0132] The processor 111 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0133] The memory 112 can be an internal storage unit of the terminal device 110, for example, a hard disk or a memory of the terminal device 110. The memory 112 can also be an external storage device of the terminal device 110, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal device 110. Further, the memory 112 can include both the internal storage unit and the external storage device of the terminal device 110. The memory 112 can also store the computer program 113 and other programs and data required by the terminal device 110. The memory 112 can also be used to temporarily store data that has been output or will be output.

[0134] An embodiment of the present application further provides a computer readable storage medium storing a computer program. The computer program, when executed by a processor, can implement the steps of the above-mentioned various method embodiments. The computer program includes computer program code, which can be in the form of source code, object code, executable files or some intermediate forms, etc. The computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0135] The above are preferred embodiments of the present application, which do not limit the protection scope of the present application. Therefore, any equivalent changes made according to the methods, principles and structures of the present application should be covered within the protection scope of the present application.

Claims

1. A GIS equipment monitoring method based on image recognition, applicable to GIS equipment, wherein the GIS equipment comprises a housing, a sealing flange is installed at a connection of the housing, and the housing is filled with sulfur hexafluoride gas, characterized in that: The method comprises: Obtaining a grayscale image to be detected of the GIS device; determining a first target region in the grayscale image to be detected based on first grayscale value information of each pixel point in the grayscale image to be detected, wherein the second grayscale value information of the first target region is smaller than the third grayscale value information of an adjacent region, and the adjacent region is used to describe a region adjacent to the first target region; Based on the grayscale image to be detected and a preset target detection algorithm, determining first position information corresponding to the first target area in the grayscale image to be detected and second position information corresponding to the second target area, wherein the second target area is used to describe the area corresponding to the sealing flange in the grayscale image to be detected; Determining predicted location information based on the first location information and the second location information, wherein the predicted location information is used to describe a predicted location corresponding to a gas leakage point in the GIS device; The step of determining the first target area in the grayscale image to be detected according to the first grayscale value information of each pixel in the grayscale image to be detected includes: Obtaining first grayscale value information corresponding to each pixel in the grayscale image to be detected; Comparing the first grayscale value information corresponding to each of the pixel points with a preset first grayscale threshold, respectively, to determine a target pixel point, wherein the fourth grayscale value information of the target pixel point is less than or equal to the first grayscale threshold; For each target pixel: Obtain the fifth grayscale value information of adjacent pixels; generating grayscale difference information according to the fifth grayscale value information and the fourth grayscale value information; comparing the grayscale difference information with a preset second grayscale threshold; If the grayscale difference information is less than or equal to the second grayscale threshold, merging the adjacent pixel points and the target pixel point to generate a first target area; Wherein, after obtaining the first grayscale value information corresponding to each pixel point in the grayscale image to be detected, the method further includes: For each of the pixels: comparing the first grayscale value information with a preset third grayscale threshold; If the first grayscale value information is less than or equal to the third grayscale threshold, calculating the difference between the first grayscale value information and a preset grayscale correction value to generate first optimized grayscale value information corresponding to the pixel point; If the first grayscale value information is greater than the third grayscale threshold, calculating the sum of the first grayscale value information and a preset grayscale correction value to generate second optimized grayscale value information corresponding to the pixel point; Accordingly, the step of comparing the first grayscale value information corresponding to each pixel with a preset first grayscale threshold to determine the target pixel includes: For each of the pixels: Comparing the first optimized grayscale value information corresponding to the pixel point with a preset first grayscale threshold to determine a target pixel point; or The second optimized grayscale value information corresponding to the pixel point is compared with a preset first grayscale threshold to determine the target pixel point.

2. The method according to claim 1, characterized in that The determining the predicted position information according to the first position information and the second position information includes: Determine a first overlapping area according to the first position information and the second position information, wherein the first overlapping area is used to describe an area where the first position information and the second position information overlap; Acquire third position information of the first overlapping area, and determine the third position information as the predicted position information.

3. The method according to claim 2, characterized in that Before determining the first overlapping area according to the first position information and the second position information, the method further includes: Obtaining historical leakage position information of the sealing flange; Accordingly, determining a first overlapping area according to the first position information and the second position information includes: A second overlapping area is determined according to the first location information, the second location information, and historical air leakage location information, wherein the second overlapping area is used to describe an area where the first location information, the second location information, and the historical air leakage location information overlap.

4. The method according to claim 1, wherein Before obtaining the grayscale image to be detected of the GIS device, the method further includes: Based on a preset infrared thermal imager, an infrared image of the GIS device to be inspected is obtained; Accordingly, the step of obtaining the grayscale image to be detected of the GIS device includes: Grayscale processing is performed on the infrared image to be detected to generate a grayscale image to be detected of the GIS device.

5. A GIS equipment monitoring system based on image recognition, applicable to GIS equipment, wherein the GIS equipment comprises a housing, a sealing flange is installed at the connection of the housing, and the housing is filled with sulfur hexafluoride gas, characterized in that: The system comprises: Grayscale image acquisition module to be detected: used to obtain the grayscale image to be detected of the GIS device; A first target region determining module is configured to determine a first target region in the grayscale image to be detected based on first grayscale value information of each pixel point in the grayscale image to be detected, wherein the second grayscale value information of the first target region is smaller than the third grayscale value information of an adjacent region, and the adjacent region is used to describe a region adjacent to the first target region; A position information determination module is configured to determine, based on the grayscale image to be detected and a preset target detection algorithm, first position information corresponding to the first target area in the grayscale image to be detected and second position information corresponding to the second target area in the grayscale image to be detected, wherein the second target area is used to describe the area corresponding to the sealing flange in the grayscale image to be detected; A predicted location information determination module is configured to determine predicted location information based on the first location information and the second location information, wherein the predicted location information is used to describe the predicted location corresponding to the gas leakage point in the GIS device; The first target area determination module includes: A first grayscale value information acquisition submodule: used to obtain first grayscale value information corresponding to each pixel point in the grayscale image to be detected; a target pixel determination submodule configured to compare the first grayscale value information corresponding to each pixel with a preset first grayscale threshold to determine a target pixel, wherein the fourth grayscale value information of the target pixel is less than or equal to the first grayscale threshold; A fifth grayscale value information acquisition submodule is configured to acquire, for each target pixel point, fifth grayscale value information of adjacent pixels; Grayscale difference information generating submodule: used for generating grayscale difference information according to the fifth grayscale value information and the fourth grayscale value information; Grayscale difference information comparison submodule: used to compare the grayscale difference information with a preset second grayscale threshold; A first target region generating submodule: configured to merge the adjacent pixels and the target pixel to generate a first target region if the grayscale difference information is less than or equal to the second grayscale threshold; Wherein, the system further includes: A first grayscale value information comparison module is configured to compare the first grayscale value information with a preset third grayscale threshold for each pixel point; A first optimized grayscale value information generating module is configured to calculate the difference between the first grayscale value information and a preset grayscale correction value to generate first optimized grayscale value information corresponding to the pixel point if the first grayscale value information is less than or equal to the third grayscale threshold; A second optimized grayscale value information generating module is configured to calculate the sum of the first grayscale value information and a preset grayscale correction value to generate second optimized grayscale value information corresponding to the pixel point if the first grayscale value information is greater than the third grayscale threshold; Accordingly, the target pixel determination submodule includes: A first target pixel point determination unit is configured to compare, for each pixel point, the first optimized grayscale value information corresponding to the pixel point with a preset first grayscale threshold value to determine the target pixel point; or The second target pixel point determination unit is configured to compare the second optimized grayscale value information corresponding to the pixel point with a preset first grayscale threshold value to determine the target pixel point.

6. A terminal device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 4 are implemented.

7. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

Images